{"id":"https://openalex.org/W4283028305","doi":"https://doi.org/10.1145/3531146.3533099","title":"Measuring Representational Harms in Image Captioning","display_name":"Measuring Representational Harms in Image Captioning","publication_year":2022,"publication_date":"2022-06-20","ids":{"openalex":"https://openalex.org/W4283028305","doi":"https://doi.org/10.1145/3531146.3533099"},"language":"en","primary_location":{"id":"doi:10.1145/3531146.3533099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3531146.3533099","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3531146.3533099","source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3531146.3533099","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002575847","display_name":"Angelina Wang","orcid":"https://orcid.org/0000-0001-9140-3523"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Angelina Wang","raw_affiliation_strings":["Princeton University, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074825066","display_name":"Solon Barocas","orcid":"https://orcid.org/0000-0003-4577-466X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Solon Barocas","raw_affiliation_strings":["Microsoft Research, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052732649","display_name":"Kristen Laird","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Laird","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046348432","display_name":"Hanna Wallach","orcid":"https://orcid.org/0000-0003-3395-7186"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanna Wallach","raw_affiliation_strings":["Microsoft Research, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002575847"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":1.9089,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.90495457,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"324","last_page":"335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9564999938011169,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9542797803878784},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6545728445053101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6459789872169495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4804779589176178},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4666208028793335},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4160920977592468}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9542797803878784},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6545728445053101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459789872169495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4804779589176178},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4666208028793335},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4160920977592468}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3531146.3533099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3531146.3533099","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3531146.3533099","source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3531146.3533099","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3531146.3533099","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3531146.3533099","source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3368294025","display_name":null,"funder_award_id":"2039656","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283028305.pdf","grobid_xml":"https://content.openalex.org/works/W4283028305.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1590863605","https://openalex.org/W1861492603","https://openalex.org/W1953661235","https://openalex.org/W1956340063","https://openalex.org/W2024317643","https://openalex.org/W2067816745","https://openalex.org/W2534712034","https://openalex.org/W2575842049","https://openalex.org/W2588822708","https://openalex.org/W2600463316","https://openalex.org/W2604178507","https://openalex.org/W2748163013","https://openalex.org/W2886641317","https://openalex.org/W2903410490","https://openalex.org/W2954112064","https://openalex.org/W2962968835","https://openalex.org/W2963349562","https://openalex.org/W2963448089","https://openalex.org/W2963686907","https://openalex.org/W2964042428","https://openalex.org/W2982435932","https://openalex.org/W3133702157","https://openalex.org/W3173220247","https://openalex.org/W3173937618","https://openalex.org/W3207136799","https://openalex.org/W4288083800","https://openalex.org/W4288083803","https://openalex.org/W4312769147","https://openalex.org/W6949549905"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Previous":[0],"work":[1],"has":[2],"largely":[3],"considered":[4],"the":[5,12,35,42,80,106,117,121,127],"fairness":[6],"of":[7,15,23,29,41,92,109,112,120],"image":[8,45,51,61],"captioning":[9,46,52,62],"systems":[10],"through":[11],"underspecified":[13],"lens":[14],"\u201cbias.\u201d":[16],"In":[17],"contrast,":[18],"we":[19,100,125],"present":[20],"a":[21,49],"set":[22],"techniques":[24,88],"for":[25,39,89],"measuring":[26],"five":[27],"types":[28],"representational":[30],"harms,":[31],"as":[32,34],"well":[33],"resulting":[36,122],"measurements":[37],"obtained":[38],"two":[40],"most":[43],"popular":[44],"datasets":[47],"using":[48],"state-of-the-art":[50],"system.":[53],"Our":[54],"goal":[55],"was":[56],"not":[57,139],"to":[58,66,77,104],"audit":[59],"this":[60],"system,":[63],"but":[64],"rather":[65],"develop":[67],"normatively":[68],"grounded":[69],"measurement":[70,87,131],"techniques,":[71],"in":[72,114],"turn":[73,115],"providing":[74],"an":[75],"opportunity":[76],"reflect":[78],"on":[79],"many":[81],"challenges":[82],"involved.":[83],"We":[84,94],"propose":[85],"multiple":[86],"each":[90,110],"type":[91,111],"harm.":[93],"argue":[95],"that":[96],"by":[97],"doing":[98],"so,":[99],"are":[101],"better":[102],"able":[103],"capture":[105],"multi-faceted":[107],"nature":[108],"harm,":[113],"improving":[116],"(collective)":[118],"validity":[119],"measurements.":[123],"Throughout,":[124],"discuss":[126],"assumptions":[128],"underlying":[129],"our":[130],"approach":[132],"and":[133],"point":[134],"out":[135],"when":[136],"they":[137],"do":[138],"hold.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}